def test_gowl_vs_glasso_duality_gap_3(self):
"""
Duality Gap goes negative in this case. Should that happen?
"""
np.random.seed(680)
p = 10
blocks = [
Block(dim=p,
idx=0,
block_min_size=2,
block_max_size=6,
block_value=0.9),
Block(dim=p,
idx=1,
block_min_size=2,
block_max_size=6,
block_value=-0.9),
Block(dim=p,
idx=3,
block_min_size=2,
block_max_size=6,
block_value=-0.5),
]
theta_star, blocks, theta_blocks = generate_theta_star_gowl(p=p,
alpha=0.5,
noise=0.1,
blocks=blocks)
lam1 = 0.001 # controls sparsity
lam2 = 0.01 # encourages equality of coefficients
rho = oscar_weights(lam1, lam2, (p ** 2 - p) / 2)
theta_star = theta_star[0]
sigma = np.linalg.inv(theta_star)
n = 100
X = np.random.multivariate_normal(np.zeros(p), sigma, n)
X = standardize(X)
S = np.cov(X.T)
theta_0 = np.linalg.inv(S)
model = GOWLModel(X, S, theta_0, lam1, lam2, 'backtracking', max_iters=100000)
model.fit()
theta_gowl = model.theta_hat
gl = GraphicalLasso(max_iter=200)
gl.fit(S)
theta_glasso = gl.get_precision()
print('Non zero entries in precision matrix {}'.format(np.count_nonzero(theta_gowl)))
plot_multiple_theta_matrices_2d([theta_blocks, theta_star, theta_glasso, theta_gowl],
[f"Blocks: {len(blocks)}", 'True Theta', 'GLASSO', 'GOWL'])
_fit_evaluations(theta_star, theta_glasso, 3, 'GLASSO')
_fit_evaluations(theta_star, theta_gowl, 3, 'GOWL')
y_hat_gowl = spectral_clustering(theta=theta_gowl, K=4)
y_hat_glasso = spectral_clustering(theta=theta_glasso, K=4)
y_true = spectral_clustering(theta=theta_blocks, K=4).flatten()
_cluster_evaluations(y_true, y_hat_gowl, 'GOWL')
_cluster_evaluations(y_true, y_hat_glasso, 'GLASSO')
def test_ccgowl_vs_grab_1(self):
np.random.seed(680)
p = 10
n_blocks = 1
theta_star, blocks, theta_blocks = generate_theta_star_gowl(p=p,
alpha=0.5,
noise=0.1,
n_blocks=n_blocks,
block_min_size=2,
block_max_size=6)
theta_star = theta_star[0]
sigma = np.linalg.inv(theta_star)
n = 100
X = np.random.multivariate_normal(np.zeros(p), sigma, n)
X = standardize(X)
S = np.cov(X.T)
lam1 = 0.05263158
lam2 = 0.05263158
theta_owl = np.zeros((p, p))
model = CCGOWLModel(X, lam1, lam2)
model.fit()
theta_ccgowl = model.theta_hat
lmbda = .2
K = 10
o_size = .3 # The size of overlap, as an input parameter
max_iter = 20
tol = 1e-4
dual_max_iter = 600
dual_tol = 1e-4
theta_grab, blocks = grab.BCD(S,
lmbda=lmbda,
K=K,
o_size=o_size,
max_iter=max_iter,
tol=tol,
dual_max_iter=dual_max_iter,
dual_tol=dual_tol)
theta_grab = np.asarray(theta_grab)
print('Non zero entries in precision matrix {}'.format(np.count_nonzero(theta_owl)))
plot_multiple_theta_matrices_2d([S, theta_blocks, theta_star, theta_grab, theta_ccgowl],
['Sample Covariance', f"Blocks: {len(blocks)}", 'True Theta', 'GRAB', 'CCGOWL'])
_fit_evaluations(theta_star, theta_grab, 1, 'GRAB')
_fit_evaluations(theta_star, theta_owl, 1, 'GOWL')
y_hat_gowl = spectral_clustering(theta=theta_owl, K=2)
y_hat_grab = spectral_clustering(theta=theta_grab, K=2)
y_true = spectral_clustering(theta=theta_blocks, K=2).flatten()
_cluster_evaluations(y_true, y_hat_gowl, 'CCGOWL')
_cluster_evaluations(y_true, y_hat_grab, 'GRAB')
def test_gowl_vs_grab_1(self):
np.random.seed(680)
p = 10
n_blocks = 1
theta_star, blocks, theta_blocks = generate_theta_star_gowl(p=p,
alpha=0.5,
noise=0.1,
n_blocks=n_blocks,
block_min_size=2,
block_max_size=6)
theta_star = theta_star[0]
sigma = np.linalg.inv(theta_star)
n = 100
X = np.random.multivariate_normal(np.zeros(p), sigma, n)
X = standardize(X)
S = np.cov(X.T)
lam1 = 0.001 # controls sparsity
lam2 = 0.01 # encourages equality of coefficients
lmbda = .2
K = 10
o_size = .3 # The size of overlap, as an input parameter
max_iter = 20
tol = 1e-4
dual_max_iter = 600
dual_tol = 1e-4
theta_grab, blocks = grab.BCD(S,
lmbda=lmbda,
K=K,
o_size=o_size,
max_iter=max_iter,
tol=tol,
dual_max_iter=dual_max_iter,
dual_tol=dual_tol)
theta_grab = np.asarray(theta_grab)
model = GOWLModel(X, S, lam1, lam2, 'backtracking', max_iters=100000)
model.fit()
theta_gowl = model.theta_hat
print('Non zero entries in precision matrix {}'.format(np.count_nonzero(theta_gowl)))
plot_multiple_theta_matrices_2d([theta_blocks, theta_star, theta_grab, theta_gowl],
[f"1 Block of Size 2", 'True Theta', 'GRAB', 'GOWL'])
_fit_evaluations(theta_star, theta_grab, 1, 'GRAB')
_fit_evaluations(theta_star, theta_gowl, 1, 'GOWL')
y_hat_gowl = spectral_clustering(theta=theta_gowl, K=2)
y_hat_grab = spectral_clustering(theta=theta_grab, K=2)
y_true = spectral_clustering(theta=theta_blocks, K=2).flatten()
_cluster_evaluations(y_true, y_hat_gowl, 'GOWL')
_cluster_evaluations(y_true, y_hat_grab, 'GRAB')
def read_stock_data():
proj_root_path = pathlib.Path.cwd().parent.parent
data_path = 'data/raw/s_&_p/data.csv'
sector_path = 'data/raw/s_&_p/info.csv'
data_full_path = proj_root_path / data_path
sectors_full_path = proj_root_path / sector_path
data = pd.read_csv(data_full_path, index_col=0)
info = pd.read_csv(sectors_full_path)
data = standardize(data)
stock_names = info['V1']
sectors = info['V2']
data.columns = [f'{comp}/{gic}' for comp, gic in zip(stock_names, sectors)]
return data, data.columns
def load_gene_subset():
proj_root_path = pathlib.Path.cwd().parent.parent
data_path = 'data/processed/golub_et_al/AML_ALL_reduced_50.csv'
reactome_path = 'data/processed/golub_et_al/reactome.csv'
data_full_path = proj_root_path / data_path
reactome_full_path = proj_root_path / reactome_path
df = pd.read_csv(data_full_path)
react_df = pd.read_csv(reactome_full_path)
labels = {
k: f"{k}/{label}"
for k, label in zip(react_df['gene'].to_list(), react_df['pathway'].to_list())
}
X = df.drop([0, 1], axis=0)
X = X.drop(['Unnamed: 0'], axis=1)
X.index = pd.to_numeric(X.index)
X.sort_index(inplace=True)
X = X.astype(float)
X = standardize(X)
return X, labels